© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153034
    Prev
    Next
    INDEX
    Explanations

    comic, country, world, cure, rate, rules

    np_acts-logits-general · gemini-2.5-flash-lite

    transitioning between Approximate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ite
    0.54
    ி
    0.49
     comfy
    0.45
     bequem
    0.42
    ంబ
    0.42
     удобно
    0.42
     yoke
    0.42
     dogma
    0.41
    燧
    0.41
    өө
    0.41
    POSITIVE LOGITS
    advised
    0.46
    contrib
    0.46
     সালাম
    0.45
    지컬
    0.44
     cuốn
    0.44
    }"
    0.43
    ".[
    0.43
     تعاون
    0.43
    from
    0.42
    ंतर
    0.42
    Activations Density 0.000%

    No Known Activations